BSRGAN
The facts below are what the maker publishes about BSRGAN, checked and dated. Our editors have not written about it yet.
Plans and prices
From BSRGAN's own pricing page, checked 11 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| BSRGAN | Free | Open-source PyTorch code and pretrained models; no paid plans listed |
The facts
Each one read from BSRGAN's own pages, with the date it was checked.
What it does
- Batch processing
- Yeschecked 22 Sep 2026
- Blur
- The model uses isotropic and anisotropic Gaussian blur kernels in both high- and low-resolution spaces.checked 11 Oct 2026
- Customization
- The degradation model can be modified by changing its parameter settings and adding degradation types for a particular application.checked 11 Oct 2026
- Degradation order
- It randomly shuffles degradations instead of always applying blur, downsampling, and noise in a fixed pipeline.checked 11 Oct 2026
- Downsampling
- Supported downsampling methods include nearest, bilinear, bicubic, and down-up-sampling.checked 11 Oct 2026
- Input formats
- JPG, JPEG, PNG, PPM, BMP, TIFchecked 22 Sep 2026
- License
- The repository identifies its license as Apache-2.0.checked 11 Oct 2026
- Limitation
- The authors say the degradation model tends to be unsuited to model an already degraded low-resolution image because it has many parameters and uses random shuffling.checked 11 Oct 2026
- Maximum scale
- 4xchecked 22 Sep 2026
- Noise
- The degradation model includes Gaussian noise, JPEG compression noise, and processed camera sensor noise.checked 11 Oct 2026
- Pretrained models
- The project provides BSRGAN and BSRNet pretrained model files for download through Google Drive or Tencent Weiyun.checked 11 Oct 2026
- Purpose
- BSRGAN is a PyTorch project for blind image super-resolution and practical degradation modeling.checked 11 Oct 2026
- Research origin
- The project presents work titled “Designing a Practical Degradation Model for Deep Blind Image Super-Resolution,” accepted to ICCV 2021.checked 11 Oct 2026
- Scale factors
- The repository notes trained BSRGAN models for scale factors 2 and 4.checked 11 Oct 2026
- Support and integrations
- The page provides code, training instructions, and model download links, and does not list commercial support or product integrations.checked 11 Oct 2026
- Training
- The instructions describe training BSRNet and BSRGAN with PyTorch DataParallel or DistributedDataParallel, including a four-GPU example.checked 11 Oct 2026
- Training data
- Its degradation model synthesizes paired low- and high-quality training images from high-quality images.checked 11 Oct 2026
- Upscaling method
- aichecked 22 Sep 2026
The company
- Founded
- 2021checked 28 Sep 2026
Money
- Free plan
- Yeschecked 22 Sep 2026
Alternatives to BSRGAN
- 1
Cutout.Pro
Free planAndroidiOSWebAPI8.5From $5 a month - 2
Krea Enhancer
Free planiOSWebAPISelf-hosted8.4Free plan - 3
Bigjpg
Free planAndroidiOSWebAPI8.4$6 one-time - 4
Phot.AI
Free planAndroidiOSWebAPI8.4From $9 a month - 5
Pixelcut
Free planAndroidiOSWebAPI8.4From $8 a month - 6
Upscal
Free planiOSmacOSWindows8.3Free plan